Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/wangwei1237/agent-skills/storm-skillnpx skills add wangwei1237/agent-skills --skill storm-skillgit clone --depth 1 https://github.com/wangwei1237/agent-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/wangwei1237/agent-skills/storm-skill)<a href="https://agentmods.dev/skills/wangwei1237/agent-skills/storm-skill"><img src="https://agentmods.dev/badge/skills/wangwei1237/agent-skills/storm-skill.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00072 | $0.01381 |
| Opus 5 | $0.00036 | $0.00691 |
| Sonnet 5 | $0.00014 | $0.00276 |
| Haiku 4.5 | $0.00007 | $0.00138 |
Grade A, and why
storm scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
STORM
Use STORM to research a topic through multiple perspectives, retrieve evidence, expose contradictions, synthesize an actionable briefing, and audit the result.
STORM here abstracts Stanford OVAL's "Synthesis of Topic Outlines through Retrieval and Multi-perspective Question Asking" into an agent workflow. It preserves the core pattern: perspective-guided question asking, evidence retrieval, outline/synthesis, drafting, and polishing.
When to Use
Use this skill when the task needs:
- A nuanced briefing on a broad, contested, or high-stakes topic.
- Research grounded in external sources or a user-provided corpus.
- Multiple viewpoints before forming a recommendation.
- Contradiction, incentive, blind-spot, or evidence-quality analysis.
- A structured outline or long-form report with citations.
Do not use it for simple factual lookups, purely local code edits, or opinions that do not need research.
Core Workflow
1. Scope
Clarify or infer:
topic: the subject being researched.user_role: who will act on the findings, if relevant.output: briefing, outline, report, decision memo, test plan, roadmap, etc.source_mode: live web, repository/docs, uploaded files, database, or user-provided text.depth: quick, standard, or exhaustive.
If the topic is current, niche, medical, legal, financial, or otherwise high-risk, retrieve current sources before synthesizing. If retrieval is unavailable, state the limitation and ask for source material or proceed as an explicitly source-limited analysis.
2. Multi-Perspective Research
Research {topic} by simulating 5 expert perspectives:
- The practitioner: works with this topic every day. What do they know that academics miss? Which practical realities are usually ignored?
- The academic: has studied this topic for years. What does peer-reviewed evidence actually say? Where does evidence contradict popular belief?
- The skeptic: thinks the mainstream view is wrong. What is the strongest counterargument? What evidence do proponents tend to ignore?
- The economist: follows the money. Who benefits from the current narrative? What incentives shape the research or discourse?
- The historian: has seen similar patterns before. What historical parallels exist? What can be learned from how those cases played out?
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 134 lines · 72 tokens per session scan A 31d253881be4
storm is a skill published in the GitHub repository wangwei1237/agent-skills (4 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 72 tokens to every session and 1,381 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
nature-statistics
Audit, revise, or draft manuscript statistical reporting for Nature / high-impact journal submissions. Use when the user asks to check statistical analysis sections, p values, confidence intervals, sample size, biological versus technical replicates, randomization, blinding, multiple-comparison correction, model…
nature-citation
Add strict Nature/CNS citations to manuscript text by splitting long passages into citable segments, searching only accepted flagship and subjournal titles from Nature Portfolio, the AAAS Science family, and Cell Press, filtering by publication time range, and exporting one reference-manager-ready output by default.…
baoyu-youtube-transcript
Downloads YouTube video transcripts/subtitles and cover images by URL or video ID. Supports multiple languages, translation, chapters, and speaker identification. Caches raw data for fast re-formatting. Use when user asks to "get YouTube transcript", "download subtitles", "get captions", "YouTube字幕", "YouTube封面"…
review-plan
Review a plan by running internal reviews and a peer review in parallel and returning combined findings. Use when the user asks to "review my plan", "check my plan", "critique my plan", or wants feedback on a plan.
reply-to-pr-threads
Draft, confirm, and post replies to GitHub PR review threads. Handles per-category reply formatting, re-fetches thread resolution state so auto-resolved threads are skipped, and posts via GraphQL. Use when the user asks to "reply to PR threads", "post PR thread replies", or "draft PR reply messages".
answer-reviewer-questions
For each reviewer question on a PR, recall implementation reasoning and compose a raw answer. Use when the user asks to "answer reviewer questions", "draft answers to PR questions", or "explain reviewer questions".